© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 63690
    Prev
    Next
    INDEX
    Explanations

    frequency, period, wavelength

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hun
    -0.08
    ubi
    -0.08
    agl
    -0.07
    áĥ¦
    -0.07
    æ¶ķ
    -0.07
    æľĿå¤ķ
    -0.07
    çļĦç»ĦåIJĪ
    -0.07
    ÙĨج
    -0.07
    alore
    -0.07
    å§Ķå±Ī
    -0.07
    POSITIVE LOGITS
    åij¨æľŁçļĦ
    0.10
     frequency
    0.10
    é¢ijçİĩ
    0.10
     Frequency
    0.10
    Frequency
    0.09
    åij¨æľŁ
    0.09
     rhyth
    0.09
    frequency
    0.08
     synchronized
    0.08
    requency
    0.08
    Activations Density 0.002%

    No Known Activations